> For the complete documentation index, see [llms.txt](https://metafishtank.gitbook.io/metafishtank-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metafishtank.gitbook.io/metafishtank-docs/readme.md). # MetaFishtank Litepaper V3.3 {% hint style="info" %} This is a condensed version of the **MetaFishtank Whitepaper V3.3**. In case of any difference, the full whitepaper prevails. πŸ“„ [Read the full whitepaper](https://metaconsensusdynamicspteltd.notion.site/MetaFishtank-Whitepaper-V3-3-3be892dc898e81c1bd18fcd36bda9eb2) {% endhint %} **The Infrastructure for User-Generated Agents (UGA) on BNB Chain** > **Draw Locally, Evolve Globally.** MetaFishtank turns user creativity into persistent, programmable, AI-native game assets. Users create the Agent. **Anima Engineβ„’** interprets it. **MAP** gives it portable state. Games become interchangeable environments in which the same Agent can evolve. A drawing is not treated as a finished image. It becomes the origin of an Agent lifecycle: **Expression β†’ Interpretation β†’ Incarnation β†’ Interaction β†’ Evolution** MetaFishtank follows an **Asset-First** architecture: the Agent is the persistent constant while games become replaceable environments. The stack is organized into three functional layers: 1. **MAP β€” Protocol Layer** β€” portable identity, state, permissions and cross-game evolution. 2. **Anima Engineβ„’ β€” Intelligence Layer** β€” interpretation, validation, trait compilation, behavior and developer runtime. 3. **Tank Ecosystem β€” Application Layer** β€” official and third-party games where Agents are created, used, socialized and evolved. MetaFishtank is **not a new blockchain, rollup, or Layer 2**. The initial on-chain deployment is built on **BNB Smart Chain (BSC)**. > **BNB Chain provides the execution environment. MAP defines the asset language. Anima gives the asset life.** This repository contains the official English documentation structure for **MetaFishtank Litepaper V3.3 β€” BNB Chain Edition**. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://metafishtank.gitbook.io/metafishtank-docs/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.